摘要
创新点
本文提出利用球环构造视频哈希的方法, 用于相似视频检测。 在该方法中, 视频片段被分成若干个视频立方体, 在每个立方体中, 对视频立方体的内切球进行均匀划分, 并把球环信息投影到一副图像上, 进而对该投影图像进行非负矩阵分解, 利用分解得到的系数构造视频哈希。 本文方法沿球面切线方向提取视频时空信息, 较好的捕捉了视频时空信息变化, 提高了相似视频检测的精度和区分度。
References
Lee S, Yoo C. Robust video fingerprinting for contentbased video identification. IEEE Trans Circuits Syst Video Tech, 2008, 18: 983–988
Roover C D, Vleeschouwer C D, Lefebvre F, et al. Robust video hashing based on radial projections of key frames. IEEE Trans Signal Process, 2005, 53: 4020–4037
Coskun B, Sanku B, Memon N. Spatio-temporal transform based video hashing. IEEE Trans Multimedia, 2006, 8: 1190–1208
Wei Z K, Zhao Y, Zhu C, et al. Frame fusion for video copy detection. IEEE Trans Circuits Syst Video Tech, 2011, 21: 15–28
Nie X S, Liu J, Sun J D, et al. Robust video hashing based on representative-dispersive frames. Sci China Inf Sci, 2013, 56: 068104
Li M, Monga V. Robust video hashing via multilinear subspace projections. IEEE Trans Image Process, 2012, 21: 4397–4409
Tang Z J, Zhang S Q, Zhang S C. Robust perceptual image hashing based on ring partition and NMF. IEEE Trans Knowl Data Eng, 2014, 26: 711–724
Author information
Authors and Affiliations
Corresponding author
Electronic supplementary material
Rights and permissions
About this article
Cite this article
Nie, X., Chai, Y., Liu, J. et al. Spherical torus-based video hashing for near-duplicate video detection. Sci. China Inf. Sci. 59, 059101 (2016). https://doi.org/10.1007/s11432-016-5528-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11432-016-5528-6